Dual-Attention U-Net++ with Class-Specific Ensembles and Bayesian Hyperparameter Optimization for Precise Wound and Scale Marker Segmentation

TL;DR

This paper introduces a dual-attention U-Net++ architecture with class-specific ensembles and Bayesian hyperparameter tuning, achieving high accuracy in wound and scale marker segmentation in clinical images.

Contribution

The study presents a novel dual-attention U-Net++ model with class-specific training, Bayesian hyperparameter optimization, and ensemble techniques for improved medical image segmentation.

Findings

Achieved an F1-score of 0.8640 on benchmark dataset.

Identified EfficientNet-B7 as the optimal encoder backbone.

Enhanced segmentation accuracy with test-time augmentation.

Abstract

Accurate segmentation of wounds and scale markers in clinical images remainsa significant challenge, crucial for effective wound management and automatedassessment. In this study, we propose a novel dual-attention U-Net++ archi-tecture, integrating channel-wise (SCSE) and spatial attention mechanisms toaddress severe class imbalance and variability in medical images effectively.Initially, extensive benchmarking across diverse architectures and encoders via 5-fold cross-validation identified EfficientNet-B7 as the optimal encoder backbone.Subsequently, we independently trained two class-specific models with tailoredpreprocessing, extensive data augmentation, and Bayesian hyperparameter tun-ing (WandB sweeps). The final model ensemble utilized Test Time Augmentationto further enhance prediction reliability. Our approach was evaluated on a bench-mark dataset from the NBC 2025 & PCBBE 2025 competition. Segmentationperformance was quantified using a weighted F1-score (75% wounds, 25% scalemarkers), calculated externally by competition organizers on undisclosed hard-ware. The proposed approach achieved an F1-score of 0.8640, underscoring itseffectiveness for complex medical segmentation tasks.